CtrlK
BlogDocsLog inGet started
Tessl Logo
SkillPublic

quant-contest-trade

Use when the user asks to compare data and research teams, mature shadow scores or the event/quality/sector contest recipes.

Quality

75%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide
SecuritybySnyk

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./.agents/skills/quant-contest-trade/SKILL.md
SKILL.md
Quality
Evals
Security

Quality

Content

86%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

The content is an exemplary lean operational workflow: exact commands, concrete file paths, security and evidence-handling guardrails, and a well-signaled single external reference. The only meaningful gaps are the absent inline YAML template and the lack of an explicit error-recovery loop for failed previews or runs.

DimensionReasoningScore

Conciseness

The body is extremely lean: every line is operational instruction with zero concept explanations or padding (e.g. "Credentials belong in project environment configuration, never in the YAML or prompt"). It fully matches anchor 5 — every token earns its place and Claude's competence is assumed.

5 / 5

Actionability

Steps 3 and 4 give exact, runnable commands ("python egs/skills.py preview --config <task.yaml>", "run --config <task.yaml> --format jsonl") plus concrete subcommands (show, events, files, cancel). It falls short of anchor 5 only because the central artifact — the task YAML's required fields — is delegated to an external example file rather than shown or summarized inline.

4 / 5

Workflow Clarity

A clear 5-step sequence with a preview pre-flight checkpoint, conditional probe guidance ("Use providers --probe when backend availability is uncertain"), run-ID preservation for inspection, and explicit failure handling ("retain failed-run evidence instead of repeating paid calls"). Not anchor 5 because there is no explicit fix-and-retry loop after a failed preview or run.

4 / 5

Progressive Disclosure

No bundle files exist, and the skill is under 50 lines with well-organized sections (intro, numbered steps, closing guardrails). Its single external reference (the shared execution guide) is one level deep and clearly signaled with what it contains ("provider limits, data fields and research gates"), matching anchor 5.

5 / 5

Total

18

/

20

Passed

Description

53%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

The description has a clear, explicit trigger clause with distinctive domain terminology, giving it good discoverability and low conflict risk. However, it is entirely a "when" statement — it never explicitly says what the skill does, and its keywords are jargon-heavy without natural synonyms or variations.

Suggestions

Add an explicit capability statement before the trigger clause, e.g. "Runs the dual-team data/research contest via the platform CLI (egs/skills.py), comparing backtest results and maturing shadow scores. Use when..." so the "what" is stated, not implied.

Include natural trigger variations and synonyms users might say, such as "run the quant contest", "compare the two teams", or "graduate shadow scores", instead of only the current jargon phrasing.

Clarify what "mature shadow scores" and "contest recipes" mean operationally in one or two words each (e.g. "promote", "run") so users outside the core workflow can still recognize the skill as relevant.

DimensionReasoningScore

Specificity

The description names domain-specific activities ("compare data and research teams", "mature shadow scores", "event/quality/sector contest recipes"), but these are framed as user requests rather than the skill's capabilities, and what the skill actually does is never stated. It matches anchor 3 (domain plus 1-2 concrete actions, not comprehensive) rather than 4 because the actions describe triggers, not the skill's own functionality.

3 / 5

Completeness

An explicit and fairly specific "when" is present ("Use when the user asks to compare... or mature... contest recipes"), but the "what" is only implied through the enumerated activities and never stated as a capability. It sits between anchors 2 and 3, above 2 because the trigger clause carries substantial what-content.

3 / 5

Trigger Term Quality

Terms like "shadow scores" and "contest recipes" are phrases a user in this domain would plausibly say, and an explicit "Use when the user asks to..." clause is present. It stays at anchor 3 rather than 4 because the keywords are jargon-heavy with no synonyms or natural variations.

3 / 5

Distinctiveness Conflict Risk

Niche terms ("quant-contest-trade", "shadow scores", "event/quality/sector contest recipes") create a clear niche with minimal conflict risk. Not 5 because "compare data and research teams" is broad enough to overlap with generic comparison or analysis skills.

4 / 5

Total

13

/

20

Passed

Validation

93%

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

CriteriaDescriptionResult

relative_links

Relative link issues: 1 suspicious

Warning

Total

15

/

16

Passed

Repository

charliedream1/ai_quant_trade

Path

.agents/skills/quant-contest-trade/SKILL.md

Reviewed

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.